| 1. |
- Eriksson, Martin, et al.
(författare)
-
Monitoring and modelling open compute servers
- 2017
-
Ingår i: Proceedings IECON 2017 - 43rd Annual Conference of the IEEE Industrial Electronics Society. - Piscataway, NJ : Institute of Electrical and Electronics Engineers Inc.. - 9781538611272 ; , s. 7177-7184, s. 7177-7184
-
Konferensbidrag (refereegranskat)abstract
- Energy efficient control of server rooms in modern data centers can help reducing the energy usage of this fast growing industry. Efficient control, however, cannot be achieved without: i) continuously monitoring in real-time the behavior of the basic thermal nodes within these infrastructures, i.e., the servers; ii) analyzing the acquired data to model the thermal dynamics within the data center. Accurate data and accurate models are indeed instrumental for implementing efficient data centers cooling strategies. In this paper we focus on a class of Open Compute Servers, designed in an open-source fashion and currently deployed by Facebook. We thus propose a set of methods for collecting real-time data from these platforms and a control-oriented model describing the thermal dynamics of the CPUs and RAMs of these servers as a function of both manipulable and exogenous inputs (e.g., the CPU utilization levels and the air mass flow produced by the server's fans). We identify the parameters of this model from real data and make the results available to other researchers.
|
|
| 2. |
- Perez-Cerrolaza, Jon, et al.
(författare)
-
Artificial Intelligence for Safety-Critical Systems in Industrial and Transportation Domains: A Survey
- 2024
-
Ingår i: ACM Computing Surveys. - New York : Association for Computing Machinery. - 0360-0300 .- 1557-7341. ; 56:7
-
Tidskriftsartikel (refereegranskat)abstract
- Artificial Intelligence (AI) can enable the development of next-generation autonomous safety-critical systems in which Machine Learning (ML) algorithms learn optimized and safe solutions. AI can also support and assist human safety engineers in developing safety-critical systems. However, reconciling both cutting-edge and state-of-the-art AI technology with safety engineering processes and safety standards is an open challenge that must be addressed before AI can be fully embraced in safety-critical systems. Many works already address this challenge, resulting in a vast and fragmented literature. Focusing on the industrial and transportation domains, this survey structures and analyzes challenges, techniques, and methods for developing AI-based safety-critical systems, from traditional functional safety systems to autonomous systems. AI trustworthiness spans several dimensions, such as engineering, ethics and legal, and this survey focuses on the safety engineering dimension.
|
|
| 3. |
- Yang, Chen-Wei, 1987-
(författare)
-
Cyber-Physical Engineering of Distributed Automation Systems in Energy Domain
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The main focus of this thesis is in the domain of Energy Systems, specifically in the engi-neering of modern Smart Grid (SG) automation systems. The SG has been categorizedas a Cyber-Physical System (CPS), a complex system which exhibits tight integration between the cyber and the physical processes and their interactions in a networked envi-ronment. The complexity and the computation of the automation system are expectedto increase with the promise of a ”smart” electric grid which is capable of self-healing, self-reconfiguration and become more resilient against cyber-attacks. These automation software systems require control strategies which are distributed in execution and requirevery tight integrations and interactions between various modular software and hardware components. As the automation system becomes more software intensive, we hypothesizethat existing design practices of developing the substation automation software system would struggle to cope with the distributed design challenges of the Smart Grid and they could be substantially enhanced by the application of model-driven design, distributed software architectures and semantic models.Model-driven engineering (MDE) is a software design paradigm that leverages the use of abstraction models at different stages of the design process for engineering complex software systems. MDE is widely used in the software engineering domain and it has proven to be effective when designing and maintaining large-scale software applications.One of the core tenants of MDE is model transformation and it is considered the heartand soul of MDE. The standard modelling language that is used for MDE in software engineering is the Unified Modelling Language (UML), which is a visual language with awide array of tool support. Despite its popularity in the software domain, UML models still have its limitations. In particular, the lack of uniformed semantics between its 13different visual diagrams and the lack of formal notations. In this thesis, we proposethe Cyber-Physical Engineering (CPE) framework, an MDE framework which combines semantic models and MDE based automatic model transformation in order to auto-generate both the automation control system and the simulation plant model from thephysical and functional specifications of CPS systems.All the scientific papers included in this thesis contributes towards the proposed Cyber-Physical Engineering methodology which includes MDE using semantic models, formal modelling of functional requirements and co-simulation testing of CPS systems.The contribution of the thesis is fivefold. Firstly, the thesis proposes the CPE frame-work, which is based on the use of semantic web modelling language where logical rea-soning can be applied to the models. The modelling language that is used is the Web Ontology Language (OWL), which is a declarative language with a strong formal foun-dation based on description logic. Secondly, the extended Semantic Web Rule Language(eSWRL) is introduced which defines the constructors that are necessary for model trans-forming OWL ontology models. The eSWRL transformation language is proposed to bean extension to the widely used ontology reasoning language Semantic Web Rule Lan-guage (SWRL) in order to address the limitations of monotonicity which restricts SWRLfrom transforming ontological models. Thirdly, the implementation of the underlying transformation engine of eSWRL in SWI Prolog. Fourthly, the formal modelling of func-tional requirements in ontology is proposed which investigates the viability of using nat-ural language based functional requirements to add control flow to the auto-generated automation control system. Lastly, an automated script based co-simulation environ-ment is shown to demonstrate how black-box validation can be performed to test theauto-generated automation control system.Finally, the thesis presents the resultant CPE framework for the modelling and genera-tion of distributed CPS automation software that leverages the use of semantic web OWL models. It is aimed to provide a top-down design approach of developing distributed con-trol software for CPS systems along with the simulation model of the physical plant. Inthis thesis, we demonstrate the development process of the CPE framework and throughcase study applications, how a semi-complete distributed automation software system in IEC 61499 can be automatically generated from substation specifications in IEC 61850 and natural language based functional requirements which provide the structure and thecontrol flow of the distributed automation software respectively. An eSWRL toolchainhas been developed to facilitate the various model transformation process of the CPE framework.
|
|
| 4. |
- Derhamy, Hasan
(författare)
-
Architectural Design Principles For Industrial Internet of Things
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- As society has progressed through periods of evolution and revolution, technology hasplayed a key role as an enabler. In the same manner that mechanical machines of the1800’s drove the industrial revolution, now digitalized machines are driving another one.With this recognition of a fourth industrial revolution, the Industry 4.0 initiative wasfounded. One of the drivers of Industry 4.0 is the Industrial Internet of Things (IIoT).The IIoT is a consequence of widely present computing ubiquity and interconnected-ness. Software has become a crucial tool of almost all industries from bakeries and arts to manufacturing facilities and banking. Programming is now a required competenceand used by a variety of professions. It is not only about algorithm development, it has become more about engineering and integrating existing designs and tools. This impacts the way software is architected and drives a large body of research in the area.Software solutions are becoming more distributed, not only over multiple processes, but over heterogeneous hardware and business domains. Computing platforms could bemobile or geographically separated over large distances, exposing the solutions to network disturbances, performance degradation and security vulnerabilities.Hence, IIoT introduces complexity on a scale previously unseen in the software in-dustry. Software architecture must accommodate these heterogeneous domains and com-petencies and handle the increasing levels of complexity.This thesis proposes an architectural style for designing IIoT software architectures.The popular Service Oriented Architecture (SOA) style is not sufficient to define a com-plete architecture for IIoT applications. SOA fundamental principles are defined as loose coupling, lookup and late binding. The proposed architecture style extends these SOA principles with autonomy, specialization, data at its source and first person perspective. It preserves the benefits of SOA that models functionalities as reusable services with standardized interfaces. Thus, the proposed style helps to capture the heterogeneity of IIoT (e.g. systems, capabilities, domains, competencies etc.), while handling challenges imposed by it. The style also captures resource constraints of IIoT platforms; distri-bution of application logic across IIoT; dependence between services within IIoT; and presentation of the solution in various stakeholder perspectives.The IIoT generates large amounts of data that is subsequently stored, analysed, archived and eventually fed back into the product life cycle. Centralization of data has well known challenges. This thesis proposes a method of information extraction based on the principle of data at its source. Such data preserves implicit context, reducing the burden of semantic data within the system. Desired information is expressed through dynamic (runtime) queries. Using the queries, a path is created to retrieve the requested data. It alleviates the need for data to be stored in intermediary nodes; data remains atthe source. Thus, IIoT applications extract information and present it to requesting sys-tems without redundant source related context. This helps with issues of data ownership, access control and stale data.Another IIoT challenge tackled in this work is decentralization of Manufacturing Execution System (MES). It is motivated by a need to mitigate the impact of vulnerable shared networks on the factory floor; and by business requirements to reduce dependence on local factory infrastructure. This thesis explores a solution where functions of MES are distributed to the workstations that enables them to operate autonomously. Such autonomous workstations utilize the proposed Intelligent Product, Workflow Managerand Workflow Executor systems. Thus, MES can be decentralized to edge nodes as envisioned by Industry 4.0.
|
|
| 5. |
- Derhamy, Hasan, et al.
(författare)
-
System of System Composition based on Decentralized Service Oriented Architecture
- 2019
-
Ingår i: IEEE Systems Journal. - : IEEE. - 1932-8184 .- 1937-9234. ; 13:4, s. 3675-3686
-
Tidskriftsartikel (refereegranskat)abstract
- As society has progressed through periods of evolution and revolution, technology has played a key role as an enabler. In the same manner, mechanical machines of the 1800s drove the industrial revolution, now digitalized machines are driving another industrial revolution. Manufacturers are increasing the digital footprint on the factory floor. It is challenging to harness the vast amounts of data generated, stored, analyzed, archived, and returned. Data centralization has several well-known challenges, such as collection bottlenecks, secure retrieval, single point of failure, and data scheme fragility as data heterogeneity increases. This paper proposes a method of information distribution based on the principle of data at its source . It proposes that contextual data be used at runtime through the creation of dynamic queries that build compositions of different systems. Such system of systems (SoS) compositions handle the flow of data across its life cycle and present it as information to the initiating system. The proposal starts by creating a graph model of the Arrowhead framework. Then, building on the graph model, the query-based approach for specifying, validating, and forming the SoS is proposed. The proposed graph model allows for unambiguous description of systems and their interrelations, including security relations. The proposed composer operates on the edge computing hardware and gives the production floor the ability to extract information without impacting the overall operation of the factory.
|
|
| 6. |
- Kleyko, Denis, 1990-
(författare)
-
Vector Symbolic Architectures and their applications : Computing with random vectors in a hyperdimensional space
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The main focus of this thesis lies in a rather narrow subfield of Artificial Intelligence. As any beloved child, it has many names. The most common ones are Vector Symbolic Architectures and Hyperdimensional Computing. Vector Symbolic Architectures are a family of bio-inspired methods of representing and manipulating concepts and their meanings in a high-dimensional space (hence Hyperdimensional Computing). Information in Vector Symbolic Architectures is evenly distributed across representational units, therefore, it is said that they operate with distributed representations. Representational units can be of different nature, however, the thesis concentrates on the case when units have either binary or integer values. This thesis includes eleven scientific papers and extends the research area in three directions: theory of Vector Symbolic Architectures, their applications for pattern recognition, and unification of Vector Symbolic Architectures with other neural-like computational approaches. Previously, Vector Symbolic Architectures have been used mainly in the area of cognitive computing for representing and reasoning upon semantically bound information, for example, for analogy-based reasoning. This thesis significantly extends the applicability of Vector Symbolic Architectures to an area of pattern recognition. Pattern recognition is the area constantly enlarging its theoretical and practical horizons. Applications of pattern recognition and machine learning can be found in many areas of the present day world including health-care, robotics, manufacturing, economics, automation, transportation, etc. Despite the success in many domains pattern recognition algorithms are still far from being close to their biological vis-a-vis – the brain. In particular, one of the challenges is a large amount of training data required by conventional machine learning algorithms. Therefore, it is important to look for new possibilities in the area via exploring biologically inspired approaches.All application scenarios, which are considered in the thesis, contribute to the development of the global strategy of creating an information society. Specifically, such important applications as biomedical signal processing, automation systems, and text processing were considered. All applications scenarios used novel methods of mapping data to Vector Symbolic Architectures proposed in the thesis.In the domain of biomedical signal processing, Vector Symbolic Architectures were applied for three tasks: classification of a modality of medical images, gesture recognition, and assessment of synchronization of cardiovascular signals. In the domain of automation systems, Vector Symbolic Architectures were used for a data-driven fault isolation. In the domain of text processing, Vector Symbolic Architectures were used to search for the longest common substring and to recognize permuted words.The theoretical contributions of the thesis come in four aspects. First, the thesis proposes several methods for mapping data from its original representation into a distributed representation suitable for further manipulations by Vector Symbolic Architectures. These methods can be used for one-shot learning of patterns of generic sensor stimuli. Second, the thesis presents the analysis of an informational capacity of Vector Symbolic Architectures in the case of binary distributed representations. Third, it is shown how to represent finite state automata using Vector Symbolic Architectures. Fourth, the thesis describes the approach of combining Vector Symbolic Architectures and a cellular automaton.Finally, the thesis presents the results of unification of two computational approaches with Vector Symbolic Architectures. This is one of the most interesting cross-disciplinary contributions of the thesis. First, it is shown that Bloom Filters – an important data structure for an approximate membership query task – can be treated in terms of Vector Symbolic Architectures. It allows generalizing the process of building the filter. Second, Vector Symbolic Architectures and Echo State Networks (a special kind of recurrent neural networks) were combined together. It is possible to implement Echo State Networks using only integer values in network’s units and much simpler operation for a recurrency operation while preserving the entire dynamics of the network. It results in a simpler architecture with lower requirements on memory and operations.
|
|
| 7. |
- Palm, Emanuel, 1987-, et al.
(författare)
-
Approaching Non-Disruptive Distributed Ledger Technologies via the Exchange Network Architecture
- 2020
-
Ingår i: IEEE Access. - : IEEE. - 2169-3536. ; 8, s. 12379-12393
-
Tidskriftsartikel (refereegranskat)abstract
- The rise of distributed ledger technologies, such as R3 Corda, Hyperledger Fabric and Ethereum, has lead to a surge of interest in digitalizing different forms of contractual cooperation. By allowing for ledgers of collaboration-critical data to be reliably maintained between stakeholders without intermediaries, these solutions might enable unprecedented degrees of automation across organizational boundaries, which could have major implications for supply chain integration, medical journal sharing and many other use cases. However, these technologies tend to break with prevailing business practices by relying on code-as-contracts and distributed consensus algorithms , which can impose disruptive requirements on contract language, cooperation governance and interaction privacy. In this paper, we show how our Exchange Network architecture could be applied to avoid these disruptors. To be able to reason about the adequacy of our architecture, we present six requirements for effective contractual collaboration, which notably includes negotiable terms and effective adjudication . After outlining the architecture and our implementation of it, we describe how the latter meets our requirements by facilitating (1) negotiation, (2) user registries, (3) ownership ledgers and (4) definition sharing, as well as by only replicating ledgers between stakeholder pairs. To show how our approach compares to other solutions, we also consider how Corda, Fabric and Ethereum meet our requirements. We conclude that digital negotiation and ownership could replace many proposed uses of code-as-contracts for better compatibility with current contractual practices, as well as noting that distributed consensus algorithms are not mandatory for digital cooperation.
|
|
| 8. |
- Shokry, Mostafa, et al.
(författare)
-
Systematic survey of advanced metering infrastructure security: Vulnerabilities, attacks, countermeasures, and future vision
- 2022
-
Ingår i: Future Generation Computer Systems. - : Elsevier. - 0167-739X .- 1872-7115. ; 136, s. 358-377
-
Forskningsöversikt (refereegranskat)abstract
- There is a paradigm shift from traditional power distribution systems to smart grids (SGs) due to advances in information and communication technology. An advanced metering infrastructure (AMI) is one of the main components in an SG. Its relevance comes from its ability to collect, process, and transfer data through the internet. Although the advances in AMI and SG techniques have brought new operational benefits, they introduce new security and privacy challenges. Security has emerged as an imperative requirement to protect an AMI from attack. Currently, ensuring security is a major challenge in the design and deployment of an AMI. This study provides a systematic survey of the security of AMI systems from diverse perspectives. It focuses on attacks, mitigation approaches, and future visions. The contributions of this article are fourfold: First, the vulnerabilities that may exist in all components of an AMI are described and analyzed. Second, it considers attacks that exploit these vulnerabilities and the impact they can have on the performance of individual components and the overall AMI system. Third, it discusses various countermeasures that can protect an AMI system. Fourth, it presents the open challenges relating to AMI security as well as future research directions. The uniqueness of this review is its comprehensive coverage of AMI components with respect to their security vulnerabilities, attacks, and countermeasures. The future vision is described at the end.
|
|
| 9. |
- Vattaparambil Sudarsan, Sreelakshmi, 1996-, et al.
(författare)
-
A Model for Signatories in Cyber-Physical Systems
- 2020
-
Ingår i: Proceedings. - : IEEE. ; , s. 15-21
-
Konferensbidrag (refereegranskat)abstract
- Distributed Internet of Things and cyber-physical systems can potentially be used as agents to automatically sign events and transactions on behalf of users. To accomplish this, there is a need for a model that can represent the relationships, credentials and organizational hierarchies of people and devices, facilitating agents acting as signatories in a controlled way. This paper proposes such a model, where people in different positions are entitled to sign on behalf of organizations or departments therein and extend that to representing machines. Central in this model is the Power of Attorney (PoA), which is a self-contained and signed digital document that for a limited time and in a defined context, authorizes a particular agent (whether a person or device) to sign on behalf of a principal. Although such self-contained PoAs can be stored anywhere, we propose a conceptual architecture based on PoAs and include a signatory registry that keeps track of organizational hierarchies in terms of people and devices according to the defined model and stored PoAs in that context.
|
|
| 10. |
- Rosato, Antonello, et al.
(författare)
-
Few-shot Federated Learning in Randomized Neural Networks via Hyperdimensional Computing
- 2022
-
Ingår i: Proceedings of the International Joint Conference on Neural Networks. - : Institute of Electrical and Electronics Engineers Inc.. - 9781728186719
-
Konferensbidrag (refereegranskat)abstract
- The recent interest in federated learning has initiated the investigation for efficient models deployable in scenarios with strict communication and computational constraints. Furthermore, the inherent privacy concerns in decentralized and federated learning call for efficient distribution of information in a network of interconnected agents. Therefore, we propose a novel distributed classification solution that is based on shallow randomized networks equipped with a compression mechanism that is used for sharing the local model in the federated context. We make extensive use of hyperdimensional computing both in the local network model and in the compressed communication protocol, which is enabled by the binding and the superposition operations. Accuracy, precision, and stability of our proposed approach are demonstrated on a collection of datasets with several network topologies and for different data partitioning schemes.
|
|
